The Utility Impact of Differential Privacy on Credit Card Data in Machine Learning Algorithms

Abstract

With the development of networks and financial technologies, credit card data is increasingly being used in various fields of data analysis such as user behavior, financial transactions, and market analysis. These fields often use multiple machine learning algorithms for data mining on credit card dataset. It is worth noting that credit card data contains more diverse and comprehensive information compared to traditional data, and the dataset may contain multiple data types. At the same time, credit card data may also expose users’ privacy information. Differential privacy algorithms can add random noise to the data set, protecting sensitive information while ensuring certain data utility. However, there has been little research on the use of differential privacy algorithms on credit card data in multiple machine learning algorithms, and there has been insufficient exploration of the utility impact of differential privacy on complex credit card data. These research gaps exist in both the financial technology and privacy protection industries. Therefore, this paper applies differential privacy to credit card data in multiple classic machine learning algorithms, discusses the utility impact of various differential privacy algorithms on credit card data, and compares the performance of credit card data sets protected by differential privacy in different algorithms.